From: Roland Dreier <rdreier@cisco.com>
To: David Miller <davem@davemloft.net>
Cc: jgarzik@pobox.com, swise@opengridcomputing.com, divy@chelsio.com,
kxie@chelsio.com, netdev@vger.kernel.org,
open-iscsi@googlegroups.com, michaelc@cs.wisc.edu,
daisyc@us.ibm.com, wenxiong@us.ibm.com, bhua@us.ibm.com,
dm@chelsio.com, leedom@chelsio.com, linux-scsi@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [RFC][PATCH 1/1] cxgb3i: cxgb3 iSCSI initiator
Date: Mon, 11 Aug 2008 09:07:51 -0700 [thread overview]
Message-ID: <adafxpbzga0.fsf@cisco.com> (raw)
In-Reply-To: <20080809.224637.69833549.davem@davemloft.net> (David Miller's message of "Sat, 09 Aug 2008 22:46:37 -0700 (PDT)")
> Why show these special connections if the user cannot interact with or
> shape the stream at all like normal ones?
So that an admin can see what connections are open, so that the stack
doesn't try to reuse the same 4-tuple for another connection, etc, etc.
> And I even wonder, these days, if you probably get %90 or more of the
> gain these "optimized" iSCSI connections obtain from things like LRO.
Yes, that's the question -- are stateless offloads (plus CRC32C in the
CPU etc) going to give good enough performance that the whole TCP
offload exercise is pointless? The only issue is that I don't see how
to avoid the fundamental 3X increase in memory bandwidth that is chewed
up if the NIC can't do direct placement.
- R.
next prev parent reply other threads:[~2008-08-11 16:07 UTC|newest]
Thread overview: 71+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-07-30 0:19 [RFC][PATCH 1/1] cxgb3i: cxgb3 iSCSI initiator Karen Xie
2008-07-30 18:15 ` Shyam_Iyer
2008-07-30 18:37 ` Karen Xie
2008-07-30 19:21 ` Roland Dreier
2008-07-30 19:35 ` Jeff Garzik
2008-07-30 21:35 ` Roland Dreier
2008-08-01 0:51 ` Divy Le Ray
2008-08-07 18:45 ` Divy Le Ray
2008-08-07 20:07 ` Mike Christie
2008-08-08 18:09 ` Steve Wise
2008-08-08 22:15 ` Jeff Garzik
2008-08-08 22:20 ` Jeff Garzik
2008-08-09 7:28 ` David Miller
2008-08-09 14:04 ` Steve Wise
2008-08-10 5:14 ` Roland Dreier
2008-08-10 5:47 ` David Miller
2008-08-10 6:34 ` Herbert Xu
2008-08-10 17:57 ` Steve Wise
2008-08-11 16:09 ` Roland Dreier
2008-08-11 21:09 ` David Miller
2008-08-11 21:37 ` Roland Dreier
2008-08-11 21:51 ` David Miller
2008-08-11 23:20 ` Steve Wise
2008-08-11 23:45 ` Divy Le Ray
2008-08-12 0:22 ` David Miller
2008-08-10 5:12 ` Roland Dreier
2008-08-10 5:46 ` David Miller
2008-08-11 16:07 ` Roland Dreier [this message]
2008-08-11 21:08 ` David Miller
2008-08-11 21:39 ` Roland Dreier
2008-08-11 21:52 ` David Miller
2008-08-11 18:13 ` Rick Jones
2008-08-11 21:12 ` David Miller
2008-08-11 21:41 ` Roland Dreier
2008-08-11 21:53 ` David Miller
2008-08-12 21:57 ` Divy Le Ray
2008-08-12 22:01 ` David Miller
2008-08-12 22:02 ` David Miller
2008-08-12 22:21 ` Divy Le Ray
2008-08-13 1:57 ` Herbert Xu
2008-08-13 18:35 ` Vladislav Bolkhovitin
2008-08-13 19:29 ` Jeff Garzik
2008-08-13 20:13 ` David Miller
2008-08-14 18:24 ` Vladislav Bolkhovitin
2008-08-14 21:59 ` Nicholas A. Bellinger
2008-08-13 20:23 ` David Miller
2008-08-14 18:27 ` Vladislav Bolkhovitin
2008-08-14 18:30 ` Vladislav Bolkhovitin
2008-08-13 21:27 ` Roland Dreier
2008-08-13 22:08 ` David Miller
2008-08-13 23:03 ` Roland Dreier
2008-08-13 23:12 ` David Miller
2008-08-14 1:26 ` Tom Tucker
2008-08-14 1:37 ` David Miller
2008-08-14 1:52 ` Steve Wise
2008-08-14 2:05 ` David Miller
2008-08-14 2:44 ` Steve Wise
2008-08-14 1:57 ` Tom Tucker
2008-08-14 2:07 ` David Miller
2008-08-14 2:09 ` David Miller
2008-08-14 20:45 ` Andrew Gallatin
2008-08-14 22:23 ` David Miller
2008-08-15 12:19 ` Andrew Gallatin
2008-08-10 6:24 ` Herbert Xu
2008-08-10 9:19 ` Alan Cox
2008-08-10 12:49 ` Jeff Garzik
2008-08-10 14:54 ` James Bottomley
[not found] ` <1218380086.3418.21.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2008-08-11 16:50 ` Mike Christie
2008-07-31 1:24 ` Karen Xie
2008-07-31 12:45 ` Boaz Harrosh
2008-07-31 12:33 ` Boaz Harrosh
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=adafxpbzga0.fsf@cisco.com \
--to=rdreier@cisco.com \
--cc=bhua@us.ibm.com \
--cc=daisyc@us.ibm.com \
--cc=davem@davemloft.net \
--cc=divy@chelsio.com \
--cc=dm@chelsio.com \
--cc=jgarzik@pobox.com \
--cc=kxie@chelsio.com \
--cc=leedom@chelsio.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=michaelc@cs.wisc.edu \
--cc=netdev@vger.kernel.org \
--cc=open-iscsi@googlegroups.com \
--cc=swise@opengridcomputing.com \
--cc=wenxiong@us.ibm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).